AI Staff Engineer| Hybrid: Chicago, IL or NYC, NY
About The Position
Circana is building an agentic ecosystem on the industry's richest view of consumer behavior: intelligent systems that reason, plan, and act across the data the world's largest brands and retailers run on. This is a Forward Deployed Engineer (FDE) role. FDEs embed with the teams who run Circana's business, in operations, client service and product, and turn what those teams know into working software: AI agents where judgment is needed, automations where a rule is enough, and the MCP servers and integrations that let both reach our systems. You will work in a small pod with a principal engineer and domain experts, build on Circana's agent platform and tooling, and own whether the result works in production. FDEs move between engagements: embedded builds with a business team, shared platform components, and client-facing solutions.
Requirements
- A track record of shipping production software that real users depended on, including AI or agentic systems.
- Strong integration engineering: APIs, data pipelines, databases, and systems you did not build.
- Deep practical craft with models: context management, prompting, structured outputs, and tool design.
- Strong Python; productive in an unfamiliar codebase quickly.
- Fluent daily use of agentic coding tools; Claude Code preferred.
- Comfortable working directly with non-technical experts, and persistent in getting to how a process actually works.
- Experience running workloads on a major cloud platform; ours can be learned quickly.
- Clear written communication under time pressure.
- Demonstrated self-direction: work you initiated, built, or fixed without being asked.
Nice To Haves
- Prior forward deployed, solutions, or field engineering experience.
- Agentic systems in production, across multiple model families.
- Hands-on experience with an agent orchestration framework (Google ADK, LangGraph, Microsoft Agent Framework, Claude Agent SDK, or similar) on GCP Vertex AI, Azure AI Foundry, or a comparable AI stack.
- Working TypeScript and solid SQL.
- Front end capability: React, TypeScript, CopilotKit or similar.
- Workflow orchestration (Airflow or similar) and large transactional datasets.
- Evaluation and observability tooling; contributions to agent frameworks or MCP servers.
Responsibilities
- Embed with domain experts and the engineers who own the underlying systems.
- Learn how the work really happens, including the exceptions, and resolve ambiguity at the source.
- Decide, step by step, whether the work calls for a deterministic automation, an agent, or a person, and build whichever it is.
- Build agents end to end: tools, MCP servers, context and prompt design, plan construction, tool result shaping, and guardrails.
- Build integrations into real enterprise systems, including ones with thin documentation or no API: REST services, databases, file-based feeds, and schedulers.
- Build and maintain the evaluation sets, graders and regression suites that measure whether a solution is right against ground truth; investigate failures down to the step that caused them.
- Debug from traces: reproduce, isolate, fix, and add the test that prevents recurrence.
- Automate the development loop itself: turn repeated manual work into commands, hooks, and subagents.
- Move decisions forward with working prototypes.
Benefits
- paid time off
- medical/dental/vision insurance
- 401(k)
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
